{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LFLMFYVP7R73QDRWTHLVQLZGAX","short_pith_number":"pith:LFLMFYVP","schema_version":"1.0","canonical_sha256":"5956c2e2affc7fb80e3699d7582f2605f8e65bb2eb4f91cc21caefa8862094ed","source":{"kind":"arxiv","id":"2409.15204","version":3},"attestation_state":"computed","paper":{"title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Duc-Thieu Luu-Van, Hieu Dinh Vo, Son Nguyen, Thanh-Phat Nguyen, Thu-Trang Nguyen, Tuan-Dung Bui","submitted_at":"2024-09-23T16:51:43Z","abstract_excerpt":"Code completion is essential in software development, helping developers by predicting code snippets based on context. Among completion tasks, Method Body Completion (MBC) is particularly challenging as it involves generating complete method bodies based on their signatures and context. This task becomes significantly harder in large repositories, where method bodies must integrate repositoryspecific elements such as custom APIs, inter-module dependencies, and project-specific conventions. In this paper, we introduce RAMBO, a novel RAG-based approach for repository-level MBC. Instead of retrie"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.15204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SE","submitted_at":"2024-09-23T16:51:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88463ef107326c00fbf9cdb6c430d21cae82e8e4d612b329510f6ea1a72dac9e","abstract_canon_sha256":"9f64190d936c0b5f64e0139e14588e738545cdfdc8ff8100524653c6225ec362"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:14.123917Z","signature_b64":"+0BMaFlQtW0sf5AOKuyVJnJbmT/4eJDQ0GgePq3ySvrP450crSyKFW173eupue/W7crQyv9J0bQAvETHaD7/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5956c2e2affc7fb80e3699d7582f2605f8e65bb2eb4f91cc21caefa8862094ed","last_reissued_at":"2026-07-05T11:47:14.123351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:14.123351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Duc-Thieu Luu-Van, Hieu Dinh Vo, Son Nguyen, Thanh-Phat Nguyen, Thu-Trang Nguyen, Tuan-Dung Bui","submitted_at":"2024-09-23T16:51:43Z","abstract_excerpt":"Code completion is essential in software development, helping developers by predicting code snippets based on context. Among completion tasks, Method Body Completion (MBC) is particularly challenging as it involves generating complete method bodies based on their signatures and context. This task becomes significantly harder in large repositories, where method bodies must integrate repositoryspecific elements such as custom APIs, inter-module dependencies, and project-specific conventions. In this paper, we introduce RAMBO, a novel RAG-based approach for repository-level MBC. Instead of retrie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15204","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.15204/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.15204","created_at":"2026-07-05T11:47:14.123413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15204v3","created_at":"2026-07-05T11:47:14.123413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15204","created_at":"2026-07-05T11:47:14.123413+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFLMFYVP7R73","created_at":"2026-07-05T11:47:14.123413+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFLMFYVP7R73QDRW","created_at":"2026-07-05T11:47:14.123413+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFLMFYVP","created_at":"2026-07-05T11:47:14.123413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03921","citing_title":"Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX","json":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX.json","graph_json":"https://pith.science/api/pith-number/LFLMFYVP7R73QDRWTHLVQLZGAX/graph.json","events_json":"https://pith.science/api/pith-number/LFLMFYVP7R73QDRWTHLVQLZGAX/events.json","paper":"https://pith.science/paper/LFLMFYVP"},"agent_actions":{"view_html":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX","download_json":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX.json","view_paper":"https://pith.science/paper/LFLMFYVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15204&json=true","fetch_graph":"https://pith.science/api/pith-number/LFLMFYVP7R73QDRWTHLVQLZGAX/graph.json","fetch_events":"https://pith.science/api/pith-number/LFLMFYVP7R73QDRWTHLVQLZGAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX/action/storage_attestation","attest_author":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX/action/author_attestation","sign_citation":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX/action/citation_signature","submit_replication":"https://pith.science/pith/LFLMFYVP7R73QDRWTHLVQLZGAX/action/replication_record"}},"created_at":"2026-07-05T11:47:14.123413+00:00","updated_at":"2026-07-05T11:47:14.123413+00:00"}